[ { "step": 0, "val_loss": 5.74427547454834, "tok_per_s": 0.0 }, { "step": 0, "train_loss": 5.699902534484863, "lr": 1e-06, "grad_norm": 19.84527391869083 }, { "step": 400, "train_loss": 2.291149616241455, "lr": 0.00040100000000000004, "grad_norm": 1.931078807903482 }, { "step": 500, "val_loss": 4.157647836208343, "tok_per_s": 4852.333099506715 }, { "step": 800, "train_loss": 2.074878454208374, "lr": 0.0008010000000000001, "grad_norm": 1.5324353944369182 }, { "step": 1000, "val_loss": 3.9357661247253417, "tok_per_s": 7721.311855444091 }, { "step": 1200, "train_loss": 1.9981571435928345, "lr": 0.000988964669915361, "grad_norm": 1.0875002870850503 }, { "step": 1500, "val_loss": 3.95663743019104, "tok_per_s": 9621.31003560233 }, { "step": 1600, "train_loss": 1.9472236633300781, "lr": 0.0009042005118087267, "grad_norm": 0.9581416291185608 }, { "step": 2000, "val_loss": 3.569637668132782, "tok_per_s": 10987.757272157023 }, { "step": 2000, "train_loss": 1.917717456817627, "lr": 0.0007495464131639923, "grad_norm": 0.9882976403217391 }, { "step": 2400, "train_loss": 1.98982572555542, "lr": 0.0005517434726252113, "grad_norm": 0.9501996932857405 }, { "step": 2500, "val_loss": 3.7795361280441284, "tok_per_s": 12020.922136834208 }, { "step": 2800, "train_loss": 1.4463109970092773, "lr": 0.00034499361559483973, "grad_norm": 0.6110892880221367 }, { "step": 3000, "val_loss": 3.4600685477256774, "tok_per_s": 12828.544871667003 }, { "step": 3200, "train_loss": 1.6552293300628662, "lr": 0.00016504577061691466, "grad_norm": 0.7009332638197441 }, { "step": 3500, "val_loss": 3.4641281962394714, "tok_per_s": 13474.169598800208 }, { "step": 3600, "train_loss": 1.8567768335342407, "lr": 4.301455486296946e-05, "grad_norm": 0.978938501395806 }, { "step": 4000, "val_loss": 3.544374966621399, "tok_per_s": 14002.86140952401 }, { "step": 4000, "train_loss": 1.5688297748565674, "lr": 2.741556527352529e-10, "grad_norm": 0.7175795322111136 } ]